Security / AI Security Research
A Noma Security research post detailing a prompt-injection flaw in GitHub Agentic Workflows, with attack flow, proof-of-concept evidence, and security recommendations.
The page clearly documents an AI-agent security finding rather than a generic blog post: it explains the agentic workflow, the attack path, the leaked private-repo data, and includes proof-of-concept references plus mitigation guidance. That gives enough substance for a useful directory entry focused on AI security research.
The page is a single research article, so it does not describe a product, API, or reusable tool. It also leaves some practical details open, such as the exact affected GitHub configuration scope and whether the issue has been fully patched in all environments.
Last evaluated 54 days ago. Current rank #1698. Down 1 spot in the rankings.
Open-source security scanner for AI agents, MCP servers, and agent skills. It auto-discovers installed agent components and checks them for prompt injection, tool poisoning, secrets, malware payloads, and related risks.
Self-hosted AI security testing platform for authorized pentesting and bug bounty workflows, with a local web UI, live agent telemetry, verified findings, and branded PDF reports.
GitHub Marketplace app from NeuraLegion that scans apps and APIs for vulnerabilities, proposes fixes, and validates remediations inside GitHub workflows.
Belay is an open-source, local-first security layer for AI coding agents. It blocks dangerous commands, secret leaks, prompt injection, and risky MCP tool calls, with human approval flows and support for multiple agents.
